youtube_dl/extractor/liveleak.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import int_or_none
   7
   8
   9 class LiveLeakIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
  11     _TESTS = [{
  12         'url': 'http://www.liveleak.com/view?i=757_1364311680',
  13         'md5': '0813c2430bea7a46bf13acf3406992f4',
  14         'info_dict': {
  15             'id': '757_1364311680',
  16             'ext': 'mp4',
  17             'description': 'extremely bad day for this guy..!',
  18             'uploader': 'ljfriel2',
  19             'title': 'Most unlucky car accident',
  20             'thumbnail': r're:^https?://.*\.jpg$'
  21         }
  22     }, {
  23         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
  24         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
  25         'info_dict': {
  26             'id': 'f93_1390833151',
  27             'ext': 'mp4',
  28             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
  29             'uploader': 'ARD_Stinkt',
  30             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
  31             'thumbnail': r're:^https?://.*\.jpg$'
  32         }
  33     }, {
  34         # Prochan embed
  35         'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
  36         'md5': '42c6d97d54f1db107958760788c5f48f',
  37         'info_dict': {
  38             'id': '4f7_1392687779',
  39             'ext': 'mp4',
  40             'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing...  I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
  41             'uploader': 'CapObveus',
  42             'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
  43             'age_limit': 18,
  44         },
  45         'skip': 'Video is dead',
  46     }, {
  47         # Covers https://github.com/rg3/youtube-dl/pull/5983
  48         # Multiple resolutions
  49         'url': 'http://www.liveleak.com/view?i=801_1409392012',
  50         'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
  51         'info_dict': {
  52             'id': '801_1409392012',
  53             'ext': 'mp4',
  54             'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.',
  55             'uploader': 'bony333',
  56             'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
  57             'thumbnail': r're:^https?://.*\.jpg$'
  58         }
  59     }, {
  60         # Covers https://github.com/rg3/youtube-dl/pull/10664#issuecomment-247439521
  61         'url': 'http://m.liveleak.com/view?i=763_1473349649',
  62         'add_ie': ['Youtube'],
  63         'info_dict': {
  64             'id': '763_1473349649',
  65             'ext': 'mp4',
  66             'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
  67             'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
  68             'uploader': 'Ziz',
  69             'upload_date': '20160908',
  70             'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
  71         },
  72         'params': {
  73             'skip_download': True,
  74         },
  75     }]
  76
  77     @staticmethod
  78     def _extract_urls(webpage):
  79         return re.findall(
  80             r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[if]=[\w_]+[^"]+)"',
  81             webpage)
  82
  83     def _real_extract(self, url):
  84         video_id = self._match_id(url)
  85         webpage = self._download_webpage(url, video_id)
  86
  87         video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
  88         video_description = self._og_search_description(webpage)
  89         video_uploader = self._html_search_regex(
  90             r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
  91         age_limit = int_or_none(self._search_regex(
  92             r'you confirm that you are ([0-9]+) years and over.',
  93             webpage, 'age limit', default=None))
  94         video_thumbnail = self._og_search_thumbnail(webpage)
  95
  96         entries = self._parse_html5_media_entries(url, webpage, video_id)
  97         if not entries:
  98             # Maybe an embed?
  99             embed_url = self._search_regex(
 100                 r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
 101                 webpage, 'embed URL')
 102             return {
 103                 '_type': 'url_transparent',
 104                 'url': embed_url,
 105                 'id': video_id,
 106                 'title': video_title,
 107                 'description': video_description,
 108                 'uploader': video_uploader,
 109                 'age_limit': age_limit,
 110             }
 111
 112         info_dict = entries[0]
 113
 114         for a_format in info_dict['formats']:
 115             if not a_format.get('height'):
 116                 a_format['height'] = int_or_none(self._search_regex(
 117                     r'([0-9]+)p\.mp4', a_format['url'], 'height label',
 118                     default=None))
 119
 120         self._sort_formats(info_dict['formats'])
 121
 122         info_dict.update({
 123             'id': video_id,
 124             'title': video_title,
 125             'description': video_description,
 126             'uploader': video_uploader,
 127             'age_limit': age_limit,
 128             'thumbnail': video_thumbnail,
 129         })
 130
 131         return info_dict
 132
 133
 134 class LiveLeakEmbedIE(InfoExtractor):
 135     _VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[if])=(?P<id>[\w_]+)'
 136
 137     # See generic.py for actual test cases
 138     _TESTS = [{
 139         'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191',
 140         'only_matching': True,
 141     }, {
 142         'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1',
 143         'only_matching': True,
 144     }]
 145
 146     def _real_extract(self, url):
 147         mobj = re.match(self._VALID_URL, url)
 148         kind, video_id = mobj.group('kind', 'id')
 149
 150         if kind == 'f':
 151             webpage = self._download_webpage(url, video_id)
 152             liveleak_url = self._search_regex(
 153                 r'logourl\s*:\s*(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
 154                 webpage, 'LiveLeak URL', group='url')
 155         elif kind == 'i':
 156             liveleak_url = 'http://www.liveleak.com/view?i=%s' % video_id
 157
 158         return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())